© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1011
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/qwen2.5-7B-it-layer-20-saes/pile/matryoshka/k-100
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åį³åı¯
    -0.20
    oby
    -0.19
     Vo
    -0.19
    \OptionsResolver
    -0.18
    ++++
    -0.18
     Bottom
    -0.18
    Å¡e
    -0.18
    oce
    -0.18
    pec
    -0.18
     wonder
    -0.17
    POSITIVE LOGITS
    $MESS
    0.23
     },{
    0.23
    ','%
    0.22
    ."},↵
    0.21
     ********************************************************************************
    0.21
    buquerque
    0.20
    ê¹ĥ
    0.20
    <=$
    0.20
     Gratuit
    0.20
    szÄĻ
    0.20
    Activations Density 0.000%

    No Known Activations